Best AI papers explained

440 Episodo

1. Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

   Publicado: 26/5/2025
2. Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment

   Publicado: 26/5/2025
3. Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

   Publicado: 26/5/2025
4. Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

   Publicado: 26/5/2025
5. UFT: Unifying Supervised and Reinforcement Fine-Tuning

   Publicado: 26/5/2025
6. Understanding High-Dimensional Bayesian Optimization

   Publicado: 26/5/2025
7. Inference time alignment in continuous space

   Publicado: 25/5/2025
8. Efficient Test-Time Scaling via Self-Calibration

   Publicado: 25/5/2025
9. Conformal Prediction via Bayesian Quadrature

   Publicado: 25/5/2025
10. Predicting from Strings: Language Model Embeddings for Bayesian Optimization

    Publicado: 25/5/2025
11. Self-Evolving Curriculum for LLM Reasoning

    Publicado: 25/5/2025
12. Online Decision-Focused Learning in Dynamic Environments

    Publicado: 25/5/2025
13. FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

    Publicado: 25/5/2025
14. Reward Shaping from Confounded Offline Data

    Publicado: 25/5/2025
15. Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

    Publicado: 25/5/2025
16. Understanding Best-of-N Language Model Alignment

    Publicado: 25/5/2025
17. Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent

    Publicado: 24/5/2025
18. Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models

    Publicado: 24/5/2025
19. Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation

    Publicado: 24/5/2025
20. The Parallel Knowledge Gradient Method for Batch Bayesian Optimization

    Publicado: 24/5/2025